© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 396
    Prev
    Next
    INDEX
    Explanations

    JavaScript variable declarations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of variable declarations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abouts
    -0.81
    papers
    -0.80
    gard
    -0.78
    ocene
    -0.75
    impact
    -0.73
    stem
    -0.72
    æĪ¦
    -0.71
    furt
    -0.70
    Redd
    -0.70
    skirts
    -0.69
    POSITIVE LOGITS
     seq
    0.70
    Conn
    0.69
    ļéĨĴ
    0.69
     Conn
    0.68
     proc
    0.67
     expr
    0.66
    args
    0.66
     Return
    0.65
     fn
    0.65
     TRANS
    0.65
    Activations Density 0.017%

    No Known Activations